INDEX

Explanations

phrases that suggest conditional scenarios or situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

]")]

-0.85

ⓧ

-0.79

ValueStyle

-0.76

 LUMP

-0.72

 مشين

-0.71

 Exacts

-0.69

ThroughAttribute

-0.69

GEBURTSDATUM

-0.68

 للاسماء

-0.67

tvguidetime

-0.67

POSITIVE LOGITS

if

0.92

万一

0.79

 lest

0.74

lest

0.69

If

0.68

 Lest

0.66

sipasi

0.65

 unless

0.64

jalá

0.64

 Suppose

0.64

Activations Density 0.064%

phrases that suggest conditional scenarios or situations

No Comments

No Known Activations